Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1770 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 7.0594. Min Range: -7.0594
Max Act: 7.0594. Min Act: -0.1700
Data Index: 5547691 (Open Web Text)
Max Activating Token Index: 263
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.0594. Min Range: -7.0594
Max Act: 6.9344. Min Act: -0.1700
Data Index: 3900217 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.0594. Min Range: -7.0594
Max Act: 6.8719. Min Act: -0.1700
Data Index: 14481 (Open Web Text)
Max Activating Token Index: 855
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.0594. Min Range: -7.0594
Max Act: 6.8719. Min Act: -0.1700
Data Index: 3235973 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.0594. Min Range: -7.0594
Max Act: 6.7781. Min Act: -0.1700
Data Index: 6617991 (Open Web Text)
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.0594. Min Range: -7.0594
Max Act: 6.7781. Min Act: -0.1700
Data Index: 8076856 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.0594. Min Range: -7.0594
Max Act: 6.8094. Min Act: -0.1700
Data Index: 1365970 (Open Web Text)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.0594. Min Range: -7.0594
Max Act: 6.7781. Min Act: -0.1700
Data Index: 6868424 (Open Web Text)
Max Activating Token Index: 862
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.0594. Min Range: -7.0594
Max Act: 6.7781. Min Act: -0.1700
Data Index: 3191290 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.0594. Min Range: -7.0594
Max Act: 6.7781. Min Act: -0.1700
Data Index: 1264751 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.0594. Min Range: -7.0594
Max Act: 6.7156. Min Act: -0.1700
Data Index: 21205 (Open Web Text)
Max Activating Token Index: 933
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.0594. Min Range: -7.0594
Max Act: 6.7156. Min Act: -0.1700
Data Index: 8754933 (Open Web Text)
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.0594. Min Range: -7.0594
Max Act: 6.6531. Min Act: -0.1700
Data Index: 5207909 (Open Web Text)
Max Activating Token Index: 765
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.0594. Min Range: -7.0594
Max Act: 6.7156. Min Act: -0.1700
Data Index: 3748165 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.0594. Min Range: -7.0594
Max Act: 6.6844. Min Act: -0.1700
Data Index: 5833513 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.0594. Min Range: -7.0594
Max Act: 6.7156. Min Act: -0.1700
Data Index: 99480 (Open Web Text)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.0594. Min Range: -7.0594
Max Act: 6.6531. Min Act: -0.1700
Data Index: 829467 (Open Web Text)
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.0594. Min Range: -7.0594
Max Act: 6.6844. Min Act: -0.1700
Data Index: 1151504 (Open Web Text)
Max Activating Token Index: 689
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.0594. Min Range: -7.0594
Max Act: 6.6531. Min Act: -0.1700
Data Index: 4562613 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.0594. Min Range: -7.0594
Max Act: 6.6219. Min Act: -0.1700
Data Index: 5695656 (Open Web Text)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #19